Autonomous Vehicle Routing Using Predictive Disruptive Vehicle Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle routing systems do not adequately consider the likelihood of interactions with disruptive third-party vehicles, which can impact travel safety and efficiency, as they primarily focus on time and distance without accounting for the presence of vehicles that may detrimentally affect the route.
Innovation Solution
A computer-implemented model is developed to predict the likelihood of disruptive third-party vehicles in specific geographic regions, allowing for the selection of routes that minimize encounters with such vehicles by generating scores based on observed behavior and generating predicted routes, enabling the autonomous vehicle to avoid times and locations where disruptive vehicles are more likely to be present.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional routing based on time and distance is used, then travel efficiency is improved, but safety is worsened due to unaccounted disruptive third-party vehicles
Solution Approach 1:
The system performs preliminary identification and tracking of disruptive third-party vehicles before the autonomous vehicle reaches their predicted locations. By pre-calculating risk scores and predicting future positions of disruptive vehicles, the routing system can proactively select alternative routes that avoid potential conflicts, rather than reacting after encountering these vehicles.
Solution Approach 2:
The geographic space is segmented into risk zones based on predicted locations of disruptive third-party vehicles. Each zone is assigned a risk score that influences route selection. This segmentation allows the routing system to evaluate multiple candidate routes and select the one with the lowest cumulative risk while maintaining travel efficiency.
2Reliability
If routes avoid disruptive third-party vehicles, then safety is improved, but travel time increases due to longer alternative routes
Solution Approach 1:
The system applies partial avoidance by not completely eliminating all routes that pass near disruptive vehicles, but rather selecting routes that minimize exposure based on risk scores. The risk assessment allows the system to tolerate some proximity to disruptive vehicles when the alternative routes would cause excessive travel time delays, achieving a balanced compromise between safety and efficiency.
Solution Approach 2:
The routing system dynamically changes the weight parameters in the route optimization function based on real-time risk assessments. When disruptive vehicles are detected, the system adjusts the importance of safety parameters versus time parameters in the routing algorithm, allowing flexible trade-offs between travel time and safety based on current road conditions.
3Measurement precision
If real-time tracking of third-party vehicles is implemented, then detection accuracy is improved, but system complexity increases
Solution Approach 1:
The system uses universal tracking mechanisms that serve multiple functions: identifying disruptive vehicles, predicting their future positions, calculating risk scores, and informing route selection. By consolidating these functions into a unified tracking and prediction system rather than separate components, the system achieves high detection accuracy while managing complexity through functional integration.
Data Source
AI summary
Various technologies described herein relate to routing an autonomous vehicle based upon likelihood of interacting with a disruptive third-party vehicle. A computing system receives an origin location of an autonomous vehicle and a destination location of the autonomous vehicle. The computing system identifies a route for the autonomous vehicle to take based upon output of a computer-implemented model. The computer-implemented model is generated based upon labeled data that is indicative of observed instances of a disruptive third-party vehicle exhibiting behavior that impacts operation of an autonomous vehicle. The output of the computer-implemented model is a score that is indicative of a likelihood that the disruptive third-party vehicle will be traveling through a geographic location along a candidate route at a certain time. The score is used in part to identify the route from amongst a plurality of candidate routes. The autonomous vehicle then travels along the route.